Current limitations in predicting mRNA translation with deep learning models

The design of nucleotide sequences with defined properties is a long-standing problem in bioengineering. An important application is protein expression, be it in the context of research or the production of mRNA vaccines. The rate of protein synthesis depends on the 5' untranslated region (5�...

Descripción completa

Detalles Bibliográficos
Autores: Schlusser, Niels, Gonzalez Sevine, Asier|||0009-0009-0390-5482, Pandey, Muskan, Zavolan, Mihaela|||0000-0002-8832-2041
Tipo de recurso: artículo
Fecha de publicación:2024
País:España
Institución:Universitat Autònoma de Barcelona
Repositorio:Dipòsit Digital de Documents de la UAB
Idioma:inglés
OAI Identifier:oai:ddd.uab.cat:317831
Acceso en línea:https://ddd.uab.cat/record/317831
https://dx.doi.org/urn:doi:10.1186/s13059-024-03369-6
Access Level:acceso abierto
Palabra clave:Translation control
Deep learning
Explainable AI
Systems biology
id ES_87dd084c60e7bf1f380a3c9ee3f9400a
oai_identifier_str oai:ddd.uab.cat:317831
network_acronym_str ES
network_name_str España
repository_id_str
spelling Current limitations in predicting mRNA translation with deep learning modelsSchlusser, NielsGonzalez Sevine, Asier|||0009-0009-0390-5482Pandey, MuskanZavolan, Mihaela|||0000-0002-8832-2041Translation controlDeep learningExplainable AISystems biologyThe design of nucleotide sequences with defined properties is a long-standing problem in bioengineering. An important application is protein expression, be it in the context of research or the production of mRNA vaccines. The rate of protein synthesis depends on the 5' untranslated region (5'UTR) of the mRNAs, and recently, deep learning models were proposed to predict the translation output of mRNAs from the 5'UTR sequence. At the same time, large data sets of endogenous and reporter mRNA translation have become available. In this study, we use complementary data obtained in two different cell types to assess the accuracy and generality of currently available models for predicting translational output. We find that while performing well on the data sets on which they were trained, deep learning models do not generalize well to other data sets, in particular of endogenous mRNAs, which differ in many properties from reporter constructs. These differences limit the ability of deep learning models to uncover mechanisms of translation control and to predict the impact of genetic variation. We suggest directions that combine high-throughput measurements and machine learning to unravel mechanisms of translation control and improve construct design. The online version contains supplementary material available at 10.1186/s13059-024-03369-6.Universitat Autònoma de Barcelona. Departament de Bioquímica i de Biologia Molecular 22024-01-0120242024-01-01Articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://ddd.uab.cat/record/317831https://dx.doi.org/urn:doi:10.1186/s13059-024-03369-6reponame:Dipòsit Digital de Documents de la UABinstname:Universitat Autònoma de BarcelonaInglésengopen accesshttp://purl.org/coar/access_right/c_abf2Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, la comunicació pública de l'obra i la creació d'obres derivades, fins i tot amb finalitats comercials, sempre i quan es reconegui l'autoria de l'obra original.https://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:ddd.uab.cat:3178312026-06-06T12:50:31Z
dc.title.none.fl_str_mv Current limitations in predicting mRNA translation with deep learning models
title Current limitations in predicting mRNA translation with deep learning models
spellingShingle Current limitations in predicting mRNA translation with deep learning models
Schlusser, Niels
Translation control
Deep learning
Explainable AI
Systems biology
title_short Current limitations in predicting mRNA translation with deep learning models
title_full Current limitations in predicting mRNA translation with deep learning models
title_fullStr Current limitations in predicting mRNA translation with deep learning models
title_full_unstemmed Current limitations in predicting mRNA translation with deep learning models
title_sort Current limitations in predicting mRNA translation with deep learning models
dc.creator.none.fl_str_mv Schlusser, Niels
Gonzalez Sevine, Asier|||0009-0009-0390-5482
Pandey, Muskan
Zavolan, Mihaela|||0000-0002-8832-2041
author Schlusser, Niels
author_facet Schlusser, Niels
Gonzalez Sevine, Asier|||0009-0009-0390-5482
Pandey, Muskan
Zavolan, Mihaela|||0000-0002-8832-2041
author_role author
author2 Gonzalez Sevine, Asier|||0009-0009-0390-5482
Pandey, Muskan
Zavolan, Mihaela|||0000-0002-8832-2041
author2_role author
author
author
dc.contributor.none.fl_str_mv Universitat Autònoma de Barcelona. Departament de Bioquímica i de Biologia Molecular
dc.subject.none.fl_str_mv Translation control
Deep learning
Explainable AI
Systems biology
topic Translation control
Deep learning
Explainable AI
Systems biology
description The design of nucleotide sequences with defined properties is a long-standing problem in bioengineering. An important application is protein expression, be it in the context of research or the production of mRNA vaccines. The rate of protein synthesis depends on the 5' untranslated region (5'UTR) of the mRNAs, and recently, deep learning models were proposed to predict the translation output of mRNAs from the 5'UTR sequence. At the same time, large data sets of endogenous and reporter mRNA translation have become available. In this study, we use complementary data obtained in two different cell types to assess the accuracy and generality of currently available models for predicting translational output. We find that while performing well on the data sets on which they were trained, deep learning models do not generalize well to other data sets, in particular of endogenous mRNAs, which differ in many properties from reporter constructs. These differences limit the ability of deep learning models to uncover mechanisms of translation control and to predict the impact of genetic variation. We suggest directions that combine high-throughput measurements and machine learning to unravel mechanisms of translation control and improve construct design. The online version contains supplementary material available at 10.1186/s13059-024-03369-6.
publishDate 2024
dc.date.none.fl_str_mv 2
2024-01-01
2024
2024-01-01
dc.type.none.fl_str_mv Article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://ddd.uab.cat/record/317831
https://dx.doi.org/urn:doi:10.1186/s13059-024-03369-6
url https://ddd.uab.cat/record/317831
https://dx.doi.org/urn:doi:10.1186/s13059-024-03369-6
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
https://creativecommons.org/licenses/by/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
https://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Dipòsit Digital de Documents de la UAB
instname:Universitat Autònoma de Barcelona
instname_str Universitat Autònoma de Barcelona
reponame_str Dipòsit Digital de Documents de la UAB
collection Dipòsit Digital de Documents de la UAB
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869412493462339584
score 15,812429

Similares en LA Referencia